scientific-thinking-literature-review
系統性文獻回顧：規劃搜尋、篩選、綜合整理和檢查引用
中文翻譯
---
name: scientific-thinking-literature-review
description: 針對學術、生物醫學、技術與科學主題的系統性文獻回顧工作流程，包含搜尋規劃、來源篩選、綜合整理、引用檢查和證據紀錄。任務是尋找、篩選、綜合並引用一批學術或技術文獻時使用。
metadata:
origin: community
---
# 文獻回顧
任務是尋找、篩選、綜合並引用一批學術或技術文獻時，使用這個 skill。
## 何時使用
- 建立系統性、範圍性或敘述性的文獻回顧。
- 綜合某個研究問題的現況（state of the art）。
- 找出缺口、矛盾或未來研究方向。
- 為論文或報告準備有引用佐證的背景段落。
- 比較同儕審查論文、預印本、專利和技術報告之間的證據。
## 回顧類型
- **敘述性回顧**：廣泛的綜合整理，適合用來建立方向感。
- **範圍性回顧**：描繪概念、方法和證據缺口。
- **系統性回顧**：預先定義的流程、可重現的搜尋、明確的篩選與排除。
- **統合分析（meta-analysis）**：系統性回顧，再加上效果量的量化彙整。
問使用者需要哪種嚴謹程度。沒指定的話，探索性工作預設用範圍性回顧，要發表或做臨床主張就用系統性回顧。
## 工作流程
### 1. 定義問題
把提示轉成可以搜尋的研究問題。
臨床或生物醫學工作用 PICO：
- Population（族群）
- Intervention or exposure（介入或暴露）
- Comparator（對照）
- Outcome（結果）
技術工作則用：
- 系統或領域
- 方法或介入
- 比較基準
- 評估指標
### 2. 規劃搜尋
蒐集來源之前，先建立搜尋流程：
- 要搜尋的資料庫
- 日期範圍
- 語言
- 出版類型
- 納入條件
- 排除條件
- 精確的搜尋字串
最少需要的實用資料庫組合：
- PubMed：生物醫學與生命科學文獻。
- arXiv：CS、數學、物理、量化生物學和預印本。
- Semantic Scholar 或 Crossref：廣泛的學術探索。
- 相關時再加領域專屬來源，例如臨床試驗登記、專利資料庫、標準機構或官方技術文件。
### 3. 搜尋並記錄證據
維護一份搜尋紀錄，讓回顧可以重現：
```markdown
| Database | Date searched | Query | Filters | Results | Export |
| --- | --- | --- | --- | ---: | --- |
| PubMed | 2026-05-11 | `("CRISPR"[tiab] OR "Cas9"[tiab]) AND "sickle cell"[tiab]` | 2020:2026, English | 86 | PMID list |
| arXiv | 2026-05-11 | `CRISPR sickle cell gene editing` | q-bio, 2020:2026 | 9 | BibTeX |
```
原始的 ID、URL、DOI、摘要和筆記，要跟最後的文字分開存放。
### 4. 去重
依這個順序去重：
1. DOI
2. PMID 或 arXiv ID
3. 完全相同的標題
4. 標準化後的標題加第一作者和年份
記錄移除了多少重複。
### 5. 篩選來源
分階段篩選：
1. 標題
2. 摘要
3. 全文
做系統性工作時，要記錄排除原因：
- 族群不對
- 介入不對
- 結果不對
- 不是原始研究
- 重複
- 取不到全文
- 超出日期範圍
### 6. 擷取資料
用結構化的擷取表：
```markdown
| Study | Design | Population/Data | Method | Comparator | Outcome | Key finding | Limitations |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Author Year | RCT/cohort/review/etc. | sample or corpus | method | baseline | measured outcome | result | caveat |
```
技術論文要包含資料集、benchmark、指標、baseline 和可重現性備註。
### 7. 綜合整理
依主題歸納證據，不要一篇一篇摘要論文。
好用的綜合視角：
- 最強的證據
- 互相衝突的證據
- 方法上的弱點
- 族群或資料集的限制
- 時效與重複驗證
- 實務上的意涵
- 尚未回答的問題
依信心程度區分主張：
- **高信心**：跨來源重複驗證過的高品質證據。
- **中信心**：合理，但受限於樣本、方法或時效。
- **低信心**：早期、推測性、單一來源，或衡量薄弱。
### 8. 驗證引用
定稿之前：
- 驗證 DOI、PMID、arXiv ID 或官方 URL
- 檢查作者姓名和出版年份
- 不要為一篇論文沒有提出的主張引用它
- 預印本要標示為預印本
- 區分回顧文獻和原始證據
## 輸出範本
```markdown
# Literature Review: <Topic>
Generated: <date>
Review type: <narrative | scoping | systematic | meta-analysis>
Search window: <dates>
Databases: <list>
## Research Question
## Search Strategy
## Inclusion and Exclusion Criteria
## Evidence Summary
## Thematic Synthesis
## Gaps and Limitations
## References
## Search Log
```
## 常見陷阱
- 不要把搜尋結果的摘要片段當成證據。
- 不要把預印本、回顧文獻和原始研究混在一起卻不標示。
- 不要漏掉負面或互相衝突的發現。
- 沒有可重現的流程，就不要宣稱有系統性回顧的嚴謹度。
- 除非範圍明確限定在那個資料庫，否則不要只用單一資料庫就下廣泛的結論。英文原文
---
name: scientific-thinking-literature-review
description: Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging. Use when the task is to find, screen, synthesize, and cite a body of academic or technical literature.
metadata:
origin: community
---
# Literature Review
Use this skill when the task is to find, screen, synthesize, and cite a body of
academic or technical literature.
## When to Use
- Building a systematic, scoping, or narrative literature review.
- Synthesizing the state of the art for a research question.
- Finding gaps, contradictions, or future-work directions.
- Preparing citation-backed background sections for papers or reports.
- Comparing evidence across peer-reviewed papers, preprints, patents, and
technical reports.
## Review Types
- **Narrative review**: broad synthesis; useful for orientation.
- **Scoping review**: maps concepts, methods, and evidence gaps.
- **Systematic review**: predefined protocol, reproducible search, explicit
screening and exclusion.
- **Meta-analysis**: systematic review plus quantitative effect aggregation.
Ask the user which level of rigor is needed. If unspecified, default to a
scoping review for exploratory work and a systematic review for publication or
clinical claims.
## Workflow
### 1. Define the Question
Convert the prompt into a searchable research question.
For clinical or biomedical work, use PICO:
- Population
- Intervention or exposure
- Comparator
- Outcome
For technical work, use:
- system or domain
- method or intervention
- comparison baseline
- evaluation metric
### 2. Plan the Search
Create a search protocol before collecting sources:
- databases to search
- date range
- languages
- publication types
- inclusion criteria
- exclusion criteria
- exact search strings
Minimum useful database set:
- PubMed for biomedical and life-sciences literature.
- arXiv for CS, math, physics, quantitative biology, and preprints.
- Semantic Scholar or Crossref for broad academic discovery.
- Domain-specific sources when relevant, such as clinical-trial registries,
patent databases, standards bodies, or official technical docs.
### 3. Search and Log Evidence
Keep a search log that makes the review reproducible:
```markdown
| Database | Date searched | Query | Filters | Results | Export |
| --- | --- | --- | --- | ---: | --- |
| PubMed | 2026-05-11 | `("CRISPR"[tiab] OR "Cas9"[tiab]) AND "sickle cell"[tiab]` | 2020:2026, English | 86 | PMID list |
| arXiv | 2026-05-11 | `CRISPR sickle cell gene editing` | q-bio, 2020:2026 | 9 | BibTeX |
```
Save raw IDs, URLs, DOIs, abstracts, and notes separately from the final prose.
### 4. Deduplicate
Deduplicate in this order:
1. DOI
2. PMID or arXiv ID
3. exact title
4. normalized title plus first author and year
Record how many duplicates were removed.
### 5. Screen Sources
Screen in stages:
1. title
2. abstract
3. full text
For systematic work, record exclusion reasons:
- wrong population
- wrong intervention
- wrong outcome
- not primary research
- duplicate
- unavailable full text
- outside date range
### 6. Extract Data
Use a structured extraction table:
```markdown
| Study | Design | Population/Data | Method | Comparator | Outcome | Key finding | Limitations |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Author Year | RCT/cohort/review/etc. | sample or corpus | method | baseline | measured outcome | result | caveat |
```
For technical papers, include dataset, benchmark, metric, baseline, and
reproducibility notes.
### 7. Synthesize
Group evidence by theme rather than summarizing papers one by one.
Useful synthesis lenses:
- strongest evidence
- conflicting evidence
- methodological weaknesses
- population or dataset limits
- recency and replication
- practical implications
- unanswered questions
Separate claims by confidence:
- **High confidence**: replicated, high-quality evidence across sources.
- **Medium confidence**: plausible but limited by sample, method, or recency.
- **Low confidence**: early, speculative, single-source, or weakly measured.
### 8. Verify Citations
Before finalizing:
- verify DOI, PMID, arXiv ID, or official URL
- check author names and publication year
- do not cite a paper for a claim it does not make
- mark preprints as preprints
- distinguish reviews from primary evidence
## Output Template
```markdown
# Literature Review: <Topic>
Generated: <date>
Review type: <narrative | scoping | systematic | meta-analysis>
Search window: <dates>
Databases: <list>
## Research Question
## Search Strategy
## Inclusion and Exclusion Criteria
## Evidence Summary
## Thematic Synthesis
## Gaps and Limitations
## References
## Search Log
```
## Pitfalls
- Do not treat search snippets as evidence.
- Do not mix preprints, reviews, and primary studies without labeling them.
- Do not omit negative or conflicting findings.
- Do not claim systematic-review rigor without a reproducible protocol.
- Do not use a single database for a broad claim unless the scope is explicitly
limited to that database.